Machine Learning Evaluation of Intensified Conditioning on Haematopoietic Stem Cell Transplantation in Adult Acute Lymphoblastic Leukemia Patients

Overview

Journal Commun Med (Lond)

Publisher Nature Portfolio

Specialty General Medicine

Date 2024 Nov 25

PMID 39587218

Authors

Tomoyasu Jo

Kosuke Inoue

Tomoaki Ueda

Makoto Iwasaki

Yu Akahoshi

Satoshi Nishiwaki

Hiroki Hatsusawa

Tetsuya Nishida

Naoyuki Uchida

Ayumu Ito

Masatsugu Tanaka

Satoru Takada

Toshiro Kawakita

Shuichi Ota

Yuta Katayama

Satoshi Takahashi

Makoto Onizuka

Yuta Hasegawa

Keisuke Kataoka

Yoshinobu Kanda

Takahiro Fukuda

Ken Tabuchi

Yoshiko Atsuta

Yasuyuki Arai

Affiliations

Soon will be listed here.

Abstract

Background: The advantage of intensified myeloablative conditioning (MAC) over standard MAC has not been determined in haematopoietic stem cell transplantation (HSCT) for adult acute lymphoblastic leukemia (ALL) patients.

Methods: To evaluate heterogeneous effects of intensified MAC among individuals, we analyzed the registry database of adult ALL patients between 2000 and 2021. After propensity score matching, we applied a machine-learning Bayesian causal forest algorithm to develop a prediction model of individualized treatment effect (ITE) of intensified MAC on reduction in overall mortality at 1 year after HSCT.

Results: Among 2440 propensity score-matched patients, our model shows heterogeneity in the association between intensified MAC and 1-year overall mortality. Individuals in the high-benefit group (n = 1220), defined as those with ITEs greater than the median, are more likely to be younger, male, and to have higher refined Disease Risk Index (rDRI), T-cell phenotype, and grafts from related donors than those in the low-benefit group (n = 1220). The high-benefit approach (applying intensified MAC to individuals in the high-benefit group) shows the largest reduction in overall mortality at 1 year (risk difference [95% confidence interval], +5.94 percentage points [0.88 to 10.51], p = 0.011). In contrast, the high-risk approach (targeting patients with high or very high rDRI) does not achieve statistical significance (risk difference [95% confidence interval], +3.85 percentage points [-1.11 to 7.90], p = 0.063).

Conclusions: These findings suggest that the high-benefit approach, targeting patients expected to benefit from intensified MAC, has the capacity to maximize HSCT effectiveness using intensified MAC.

References

Inoue K, Adomi M, Efthimiou O, Komura T, Omae K, Onishi A . Machine learning approaches to evaluate heterogeneous treatment effects in randomized controlled trials: a scoping review. J Clin Epidemiol. 2024; 176:111538. DOI: 10.1016/j.jclinepi.2024.111538. View

Oken M, Creech R, Tormey D, Horton J, Davis T, McFadden E . Toxicity and response criteria of the Eastern Cooperative Oncology Group. Am J Clin Oncol. 1982; 5(6):649-55. View

Kantarjian H, Stein A, Gokbuget N, Fielding A, Schuh A, Ribera J . Blinatumomab versus Chemotherapy for Advanced Acute Lymphoblastic Leukemia. N Engl J Med. 2017; 376(9):836-847. PMC: 5881572. DOI: 10.1056/NEJMoa1609783. View

Austin P . Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples. Stat Med. 2009; 28(25):3083-107. PMC: 3472075. DOI: 10.1002/sim.3697. View

Inoue K, Athey S, Tsugawa Y . Machine-learning-based high-benefit approach versus conventional high-risk approach in blood pressure management. Int J Epidemiol. 2023; 52(4):1243-1256. PMC: 10396418. DOI: 10.1093/ije/dyad037. View

Konuma T, Tsukada N, Kanda J, Uchida N, Ohno Y, Miyakoshi S . Comparison of transplant outcomes from matched sibling bone marrow or peripheral blood stem cell and unrelated cord blood in patients 50 years or older. Am J Hematol. 2016; 91(5):E284-92. DOI: 10.1002/ajh.24340. View

Cortes J, Kim D, Pinilla-Ibarz J, le Coutre P, Paquette R, Chuah C . Ponatinib efficacy and safety in Philadelphia chromosome-positive leukemia: final 5-year results of the phase 2 PACE trial. Blood. 2018; 132(4):393-404. PMC: 6071555. DOI: 10.1182/blood-2016-09-739086. View

Kantarjian H, DeAngelo D, Stelljes M, Martinelli G, Liedtke M, Stock W . Inotuzumab Ozogamicin versus Standard Therapy for Acute Lymphoblastic Leukemia. N Engl J Med. 2016; 375(8):740-53. PMC: 5594743. DOI: 10.1056/NEJMoa1509277. View

Sorror M, Maris M, Storb R, Baron F, Sandmaier B, Maloney D . Hematopoietic cell transplantation (HCT)-specific comorbidity index: a new tool for risk assessment before allogeneic HCT. Blood. 2005; 106(8):2912-9. PMC: 1895304. DOI: 10.1182/blood-2005-05-2004. View

10.

Atsuta Y, Kanda J, Takanashi M, Morishima Y, Taniguchi S, Takahashi S . Different effects of HLA disparity on transplant outcomes after single-unit cord blood transplantation between pediatric and adult patients with leukemia. Haematologica. 2013; 98(5):814-22. PMC: 3640130. DOI: 10.3324/haematol.2012.076042. View

11.

Shigematsu A, Kondo T, Yamamoto S, Sugita J, Onozawa M, Kahata K . Excellent outcome of allogeneic hematopoietic stem cell transplantation using a conditioning regimen with medium-dose VP-16, cyclophosphamide and total-body irradiation for adult patients with acute lymphoblastic leukemia. Biol Blood Marrow Transplant. 2008; 14(5):568-75. DOI: 10.1016/j.bbmt.2008.02.018. View

12.

Giralt S, Ballen K, Rizzo D, Bacigalupo A, Horowitz M, Pasquini M . Reduced-intensity conditioning regimen workshop: defining the dose spectrum. Report of a workshop convened by the center for international blood and marrow transplant research. Biol Blood Marrow Transplant. 2009; 15(3):367-9. PMC: 3110087. DOI: 10.1016/j.bbmt.2008.12.497. View

13.

Arai Y, Takeda J, Aoki K, Kondo T, Takahashi S, Onishi Y . Efficiency of high-dose cytarabine added to CY/TBI in cord blood transplantation for myeloid malignancy. Blood. 2015; 126(3):415-22. PMC: 4504951. DOI: 10.1182/blood-2015-04-642652. View

14.

Arai Y, Kondo T, Shigematsu A, Tanaka J, Ohashi K, Fukuda T . Improved prognosis with additional medium-dose VP16 to CY/TBI in allogeneic transplantation for high risk ALL in adults. Am J Hematol. 2017; 93(1):47-57. DOI: 10.1002/ajh.24933. View

15.

Morita-Fujita M, Arai Y, Kondo T, Harada K, Uchida N, Toya T . Adult patients with Ph+ ALL benefit from conditioning regimen of medium-dose VP16 plus CY/TBI. Hematol Oncol. 2022; 40(5):1041-1055. PMC: 10084153. DOI: 10.1002/hon.3046. View

16.

Inoue K, Athey S, Baicker K, Tsugawa Y . Heterogeneous effects of Medicaid coverage on cardiovascular risk factors: secondary analysis of randomized controlled trial. BMJ. 2024; 386:e079377. PMC: 11417663. DOI: 10.1136/bmj-2024-079377. View

17.

Arai Y, Kondo T, Shigematsu A, Tanaka J, Ohashi K, Fukuda T . Increased non-relapse mortality due to high-dose cytarabine plus CY/TBI in BMT/PBSCT for acute lymphoblastic leukaemia in adults. Br J Haematol. 2017; 178(1):106-111. DOI: 10.1111/bjh.14652. View

18.

Fathi A, DeAngelo D, Stevenson K, Kolitz J, Asch J, Amrein P . Phase 2 study of intensified chemotherapy and allogeneic hematopoietic stem cell transplantation for older patients with acute lymphoblastic leukemia. Cancer. 2016; 122(15):2379-88. DOI: 10.1002/cncr.30037. View

19.

Gale R, Champlin R . How does bone-marrow transplantation cure leukaemia?. Lancet. 1984; 2(8393):28-30. DOI: 10.1016/s0140-6736(84)92009-9. View

20.

Stekhoven D, Buhlmann P . MissForest--non-parametric missing value imputation for mixed-type data. Bioinformatics. 2011; 28(1):112-8. DOI: 10.1093/bioinformatics/btr597. View